DaoXENatively, Volcengine Ark wants you to create an inference endpoint and call an ep-… ID. Through DaoXE, Doubao is behind the same OpenAI-compatible key as GPT, Claude and DeepSeek — you call a normal catalog ID from GET /v1/models, no Volcengine console. See the cheapest APIs guide for cost routing.
Call Doubao through DaoXE#
Use /v1/chat/completions with an exact Doubao ID from GET /v1/models. There's no endpoint provisioning step here: the catalog ID replaces the native ep-… identifier. Vision-capable variants take images via OpenAI-style content parts.
# Doubao (Volcengine Ark) natively wants endpoint IDs like "ep-2024...".
# Through DaoXE you use the catalog model ID from GET /v1/models instead —
# no endpoint provisioning, no separate Volcengine console.
curl --fail-with-body --show-error --silent \
https://daoxe.com/v1/chat/completions \
-H "Authorization: Bearer ${DAOXE_API_KEY}" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_EXACT_MODEL_ID",
"max_tokens": 64,
"messages": [{"role": "user", "content": "Reply with OK."}]
}'Doubao-specific notes#
- No ep- IDs here. Don't paste a Volcengine
ep-…string; use the catalog model ID fromGET /v1/modelsinstead. - Variants matter. Doubao ships lite/pro and vision tiers with different context and price — choose the ID deliberately.
- Multimodal via content parts. On vision-capable IDs, send images with the OpenAI-style content array.
- Exact IDs only. Read Doubao IDs from
GET /v1/models; they're account-scoped.
Payment & real cost#
Alipay / WeChat Pay / USDT — a flat 1 RMB = $1
Every method tops up at a flat 1 RMB = $1 of credit, while models bill at their official USD price. At a real ~7 RMB/USD rate, Western flagships (GPT / Claude / Gemini / Grok) come out around 1/7 of official cost (≈85% off) — and because USDT tops up the same way, USD holders abroad get the same deal. Honest caveat: cheaper domestic models (DeepSeek / Qwen / GLM) still beat going direct, just by less — it is not “everything is 1/7”. Rates move; daoxe.com/pricing is authoritative, and a small top-up verifies it.
Verify you actually get the model#
Prove the endpoint works before blaming the client — if this fails, no setting will fix it:
export DAOXE_API_KEY="your_api_key"
# List the exact model IDs your account can call
curl --fail-with-body --show-error --silent \
https://daoxe.com/v1/models \
-H "Authorization: Bearer ${DAOXE_API_KEY}"Confirm connectivity, then diff a fixed prompt against the official Volcengine/Ark API at temperature 0 to confirm the model class:
Verify us — don't trust us
Point the open benchmark at DaoXE and at the official API and compare at temperature 0. Then learn to detect model swapping so a cheaper endpoint can't quietly swap you to a smaller model.
Frequently asked questions#
Do I need a Volcengine account or an ep- endpoint?
No — through DaoXE, Doubao is behind your single key with a normal catalog ID; there's no endpoint-provisioning step.
I have an ep-… ID — do I use it?
No. That's a native Volcengine identifier. Here you use the catalog model ID from GET /v1/models.
Can Doubao take images?
Yes on vision-capable IDs — use the OpenAI-style content-parts array in the message.
How much does Doubao cost here?
Per model, account-scoped — see live pricing. Advantage vs official: typically ~30–80% below list via low-price groups.
Try DaoXE — and benchmark it yourself
One key for GPT, Claude, Gemini, DeepSeek and more. Point the open benchmark at us and compare — don't take our word for it.